© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15453
    Prev
    Next
    INDEX
    Explanations

    quotes and dialogue, especially those related to opinions or statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Quoted speech attribution

    np_acts-logits-general · gemini-2.0-flash

    quoted speech attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImageContext
    -0.58
    TagMode
    -0.50
     schein
    -0.48
    interopRequire
    -0.47
    TestingModule
    -0.46
    fillType
    -0.46
    Javadoc
    -0.44
     seeming
    -0.42
    MigrationBuilder
    -0.41
     TextAppearance
    -0.41
    POSITIVE LOGITS
     said
    2.23
     says
    1.92
    said
    1.84
    says
    1.56
    Said
    1.52
     Said
    1.42
     Says
    1.38
     SAID
    1.33
     say
    1.32
     stated
    1.31
    Activations Density 0.240%

    No Known Activations